Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _tE
    -0.07
    �
    -0.07
    _DU
    -0.07
    isAdmin
    -0.07
    _cmp
    -0.07
    㳘
    -0.07
    谇
    -0.07
     BCHP
    -0.07
    ㌃
    -0.07
    utzt
    -0.06
    POSITIVE LOGITS
    買
    0.08
     DAR
    0.07
    观看
    0.07
    ",
↵
    0.07
    פש
    0.07
    ccount
    0.07
     fetch
    0.07
    男子
    0.07
     ")↵
    0.07
    -ie
    0.07
    Act Density 0.022%

    No Known Activations